Skip to content
conftrace_
2026 EMNLP EMNLP 2026

DSPA: Dynamic SAE Steering for Data-Efficient Preference Alignment

AbstractPreference alignment is usually achieved by weight-updating training on preference data, which is costly and provides limited mechanistic visibility. We propose Dynamic SAE Steering for Preference Alignment (DSPA), an inference-time method that makes sparse autoencoder (SAE) steering prompt-conditional. From preference triples, DSPA computes a conditional-difference map linking prompt features to generation-control features; during decoding, it modifies only token-active latents, without base-model weight updates. Across Gemma-2-2B/9B and Qwen3-8B, DSPA improves MT-Bench and is competitive on AlpacaEval while preserving multiple-choice accuracy. Under restricted preference data, DSPA remains robust and can rival heavier alignment pipelines at a fraction of the compute. Finally, we audit the SAE features DSPA modifies, finding that preference directions are dominated by discourse and stylistic signals, and provide theory clarifying the conditional-difference map estimate and when top-k ablation is principled.

More from EMNLP 2026

All EMNLP 2026 papers →